我尝试使用CIFAR 10数据集构建一个机器学习模型，但遇到了一个问题，我的模型在i = 78处停止训练（循环了78次，查看代码了解更多信息）。
import torchimport torchvision.transforms as transformsfrom torchvision.datasets import CIFAR10from torchvision.transforms import ToTensorfrom torch.utils.data.dataloader import DataLoadertransform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')train_dataset = CIFAR10(root = './data', train = True, download = True, transform = transform)train_loader = DataLoader(train_dataset, batch_size = 4, shuffle = True, num_workers = 2)test_dataset = CIFAR10(root = './data', train = False, download = True, transform = transform)test_loader = DataLoader(test_dataset, batch_size = 128, shuffle = False, num_workers = 2)import torch.nn as nnimport torch.nn.functional as Fclass Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return xnet = Net()optimiser = torch.optim.SGD(model.parameters(), lr = 0.001, momentum=0.9)loss_fn = nn.CrossEntropyLoss()for epoch in range(2): running_loss = 0 for i, data in enumerate(test_loader, 0): images, labels = data outputs = model(images) loss = loss_fn(outputs, labels) optimiser.zero_grad() loss.backward() optimiser.step() running_loss += loss.item() print(i) if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0抱歉，我必须发布整个代码，因为我无法找出我犯的错误。此外，由于我无法让它工作，我尝试复制教程中的确切代码，结果它按预期工作！我也将在下面发布那个代码，
import torchimport torchvisionimport torchvision.transforms as transformstransform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')import torch.nn as nnimport torch.nn.functional as Fclass Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10)def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return xnet = Net()import torch.optim as optimcriterion = nn.CrossEntropyLoss()optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)for epoch in range(2): # loop over the dataset multiple timesrunning_loss = 0.0for i, data in enumerate(trainloader, 0): # get the inputs; data is a list of [inputs, labels] inputs, labels = data # zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() # print statistics running_loss += loss.item() if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0.0print('Finished Training')请帮助我找出错误！
回答：
查看你的主循环，你会注意到你在使用test_loader而不是train_loader。这
for epoch in range(2): running_loss = 0 for i, data in enumerate(test_loader, 0): images, labels = data outputs = model(images)应该看起来像这样：
for epoch in range(2): running_loss = 0 for i, data in enumerate(train_loader, 0): images, labels = data outputs = model(images)